Herdr Agent Board — AI skill for Claude Code
One key tiles every working, waiting or recently active AI agent in Herdr into a single board of live panes; another puts them all back.
How to install Herdr Agent Board
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open dalogax/herdr-agent-board and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Herdr Agent Board does
One key tiles every working, waiting or recently active AI agent in Herdr into a single board of live panes; another puts them all back. Works with Claude Code, Codex, OpenCode and any agent Herdr detects.
Alternatives in AI
- Project Next 14 AI Prompt Sharing — Next.js recently became the official React framework as outlined in React docs 3k ★
- Agent Teams AI — You're the boss, agents are your team 2k ★
- Paca — AI-native, free, open-source alternative to Jira, Trello, ClickUp & Monday 1.8k ★
README
herdr-agent-board
**One key to see every agent that needs you, in [Herdr](https://herdr.dev).** Tiles every working, waiting, finished or recently active agent into a single board workspace, as live panes you can type into. Another key puts every agent back exactly where it was.
Instead of walking every workspace and tab to see which agent is still working, which one is waiting on a question and which one finished while you weren't looking, press one key:
┌────────────────────────┬────────────────────────┬────────────────────────┐
│ api-refactor blocked │ docs-sweep done │ flaky-tests working │
│ Allow edit to db.ts? │ ✓ Updated 14 files │ ◐ Running suite 3/7 │
│ ❯ 1. Yes │ │ │
├────────────────────────┴───────────┬────────────┴────────────────────────┤
│ release-notes working │ infra-review idle (active 12m ago) │
│ ◐ Drafting changelog │ > │
└────────────────────────────────────┴─────────────────────────────────────┘
Answer the one that is waiting, glance at the rest, press the restore key, and your workspaces are back as they were: same tabs, same splits, same ratios, same zoom, same focus.
What gets gathered
Every agent pane Herdr detects whose state is:
| State | Meaning | Order on the board |
|---|---|---|
blocked |
waiting for your answer (approval, question) | first |
done |
finished, not yet viewed | second |
working |
running | third |
idle / unknown |
only if active in the last hour | last, most recent first |
The most urgent agents go top-left. The board holds at most 9 panes by default; the rest are left in place and the notification says how many.
Herdr does not record when an agent was last active, so the plugin keeps its own timestamp per terminal, from an event hook on every agent status change. For Claude Code it also reads the mtime of the session transcript (`~
Related Skills
Herdr Gamepad
Drive Herdr with a game controller. Patrol your AI agents, split panes and switch workspaces from the couch —
Herdr Disp Model
Display active Codex, Claude Code, Pi, and Hermes models in the Herdr agent sidebar.
AI Visualizer
Give your AI agent a face. Four full-screen visualizers. A living circuit board with a cinematic fly-through,
MCP Memory Server
Hosted persistent memory for AI agents over MCP. Tell it a recalled memory helped or misled, and it re-ranks w
Nami Win Linux
Nami for Windows and Linux. This is the Nami AI agent workbench (originally Mac-only) made available on Window
AI Prompting Guide
AI Prompting Guide: This repository aims to simplify AI prompting and explain the different functions of vario
Related Agents
Coordination Momentum
Maintain awareness of all active workstreams, prevent conflicts between parallel tasks, and ensure unblocked w
Cook Council
jeff council inquiry station. Independently investigate the exact active blocker union through one assigned le
Agent Of Empires
Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI Coding Agent Terminal Session manager via tmux and